Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    possession and relational expressions in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nero
    -0.16
    teenth
    -0.15
     Cong
    -0.14
     Cors
    -0.14
    rika
    -0.14
    ropol
    -0.14
     sig
    -0.14
    ãĥ³ãĥĨãĤ£
    -0.13
    thro
    -0.13
    ç¬
    -0.13
    POSITIVE LOGITS
    ch
    0.43
    cha
    0.36
    chw
    0.36
    chl
    0.35
    chu
    0.35
    pie
    0.34
    chie
    0.34
    pez
    0.34
    icher
    0.32
    chat
    0.31
    Act Density 0.017%

    No Known Activations